Historial de Commits

Autor SHA1 Mensaje Fecha
  Tobi Lutke 3950055708 finetune: quoted phrases, negation, and entity preservation (#247) hace 3 meses
  Tobi Lutke 785620467a refactor: reorder output format to put hyde line first hace 3 meses
  Tobi Lutke 6062dc769f Add named entity extraction to GRPO reward function hace 4 meses
  Tobi Lutke 32706a720f Refactor finetune folder: train/rl scripts with YAML configs hace 4 meses
  Tobi Lutke c35dbd6cbd Add comprehensive scoring system for query expansion hace 4 meses